Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    especially when

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﻚ
    0.52
     tikai
    0.52
    ۰
    0.51
    СТ
    0.50
     こちら
    0.48
    LIST
    0.45
    talet
    0.45
     সারাদেশে
    0.44
    ().
    0.44
     заклю
    0.43
    POSITIVE LOGITS
    al
    0.59
    if
    0.57
     if
    0.55
    in
    0.54
    féle
    0.51
    itatea
    0.51
     dacă
    0.49
    coupled
    0.49
     If
    0.49
    ből
    0.48
    Act Density 0.005%

    No Known Activations